Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier



Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded


Month Degree Awarded


First Advisor

W. Bruce Croft

Subject Categories

Artificial Intelligence and Robotics


The web contains heterogeneous information that is generated with different characteristics and is presented via different media. Social media, as one of the largest content carriers, has generated information from millions of users worldwide, creating material rapidly in all types of forms such as comments, images, tags, videos and ratings, etc. In social applications, the formation of online communities contributes to conversations of substantially broader aspects, as well as unfiltered opinions about subjects that are rarely covered in public media. Information accrued on social platforms, therefore, presents a unique opportunity to augment web sources such as Wikipedia or news pages, which are usually characterized as being more formal. The goal of this dissertation is to investigate in depth how social data can be exploited and applied in the context of three fundamental information retrieval (IR) tasks: search, fusion, and evaluation. Improving search performance has consistently been a major focus in the IR community. Given the in-depth discussions and active interactions contained in social media, we present approaches to incorporating this type of data to improve search on general web corpora. In particular, we propose two graph-based frameworks, social anchor and information network, to associate related web and social content, where information sources of diverse characteristics can be used to complement each other in a unified manner. We investigate how the enriched representation can potentially reduce vocabulary mismatch and improve retrieval effectiveness. Presenting social media content to users is valuable particularly for queries intended for time-sensitive events or community opinions. Current major search engines commonly blend results from different search services (or verticals) into core web results. Motivated by this real-world need, we explore ways to merge results from different web and social services into a single ranked list. We present an optimization framework for fusion, where impact of documents, ranked lists, and verticals can be modeled simultaneously to maximize performance. Evaluating search system performance has largely relied on creating reusable test collections in IR. Traditional ways to creating evaluation sets can require substantial manual effort. To reduce such effort, we explore an approach to automating the process of collecting pairs of queries and relevance judgments, using high quality social media, Community Question Answering (CQA). Our approach is based on the idea that CQA services support platforms for users to raise questions and to share answers, therefore encoding the associations between real user information needs and real user assessments. To demonstrate the effectiveness of our approaches, we conduct extensive retrieval and fusion experiments, as well as verify the reliability of the new, CQA-based evaluation test sets.